Skip to main content
Glama

Storywriting & Screenplay MCP Server (67 Tools)

A custom Model Context Protocol (MCP) server for AI-assisted storywriting, narrative world-building, character depth development, industry-standard screenplay generation (Fountain, Final Draft .fdx, Courier PDF), visual storyboards, generic outline ingestion, and line production analytics.


Project Structure (Refactored Clean Core Engine)

d:\Studio\MCP -Storywriting\
├── server.py                        # MCP Server entrypoint (stdio, sse, streamable-http)
├── requirements.txt                 # Dependencies
├── SETUP_GUIDE.md                   # Dedicated Claude Connector Setup Guide
├── LLM_COMPATIBILITY.md             # ChatGPT, Gemini, Kimi, DeepSeek Guide
└── story_engine/                    # Generic Core Engine
    ├── models.py                    # Schemas for Story Bible, Screenplay, Storyboards, Pitch Decks
    ├── storage.py                   # Storage persistence (.story/ directory)
    ├── batch_processor.py           # Category P: Generic Batch & Pipeline Generator
    ├── brainstorm.py                # Category A: Concept & Brainstorming (4 tools)
    ├── character.py                 # Category B: Character Architect & Dynamics (4 tools)
    ├── world.py                     # Category C: World-Building & Lore (4 tools)
    ├── beats.py                     # Category D: Structural Plotting & Beat Sheets (5 tools)
    ├── drafting.py                  # Category E: Interactive Drafting Engine (5 tools)
    ├── story_doctor.py              # Category F: Story Doctor & Continuity (4 tools)
    ├── screenplay.py                # Category G: Screenplay Adaptation & PDF/FDX (4 tools)
    ├── storyboard.py                # Category H: Storyboard & Visual Shotlists (3 tools)
    ├── dialogue_engine.py           # Category I: Character Voice & Dialogue Polish (4 tools)
    ├── analytics_engine.py          # Category J: Screenplay Timing & Analytics (4 tools)
    ├── directing_engine.py          # Category K: Visual Directing, Camera & Audio (5 tools)
    ├── production_engine.py         # Category L: Line Production & Stripboards (4 tools)
    ├── marketing_engine.py          # Category M: Pitch Deck & Marketing Suite (4 tools)
    ├── writers_room.py              # Category N: Writers' Room Mechanics (6 tools)
    └── exporters.py                 # Category O: Multi-Format Exporters & Visual Prompters (5 tools)

Related MCP server: bible-ecrivain

🛠️ How to Setup & Install This MCP Server

1. Prerequisite Installation & Python Virtual Environment Setup

  1. Open PowerShell or Terminal in the project directory:

    cd "d:\Studio\MCP -Storywriting"
  2. Create and activate a Python virtual environment:

    python -m venv venv
    .\venv\Scripts\Activate.ps1
  3. Install required packages:

    pip install -r requirements.txt

2. Setting Up in Claude Code / Claude Web (Remote Connector via Ngrok)

To connect Claude Web / Claude Code to your local MCP server:

Step 2A: One-Time Ngrok Authtoken Setup

Authenticate ngrok to resolve remote connection errors:

ngrok config add-authtoken <your-ngrok-authtoken>

Step 2B: Start the MCP Server in Streamable HTTP Mode

Run the server on port 8000:

& "d:\Studio\MCP -Storywriting\venv\Scripts\python.exe" server.py --transport streamable-http --port 8000

(Keep this terminal open!)

Step 2C: Start Ngrok HTTPS Tunnel

In a second terminal window, start ngrok:

ngrok http 8000

Copy the generated https:// forwarding URL (e.g. https://a1b2-34-56-78-90.ngrok-free.app) and append /mcp: $$\rightarrow \text{\texttt{https://a1b2-34-56-78-90.ngrok-free.app/mcp}}$$

Step 2D: Configure Claude Connector UI

  1. In Claude Web or Claude Code, open Add custom connector.

  2. Set:

    • Name: Storywriting & Screenplay Engine

    • Remote MCP server URL: https://a1b2-34-56-78-90.ngrok-free.app/mcp

  3. Click Save / Connect. All 67 tools, 4 resources, and 2 prompts will be instantly available in Claude!


3. Setting Up in ChatGPT (GPT-4o)

You can use this MCP server with ChatGPT (GPT-4o / O3-mini) in two easy ways:

  1. In your IDE MCP settings, add:

    {
      "mcpServers": {
        "storywriting-engine": {
          "command": "d:\\Studio\\MCP -Storywriting\\venv\\Scripts\\python.exe",
          "args": ["d:\\Studio\\MCP -Storywriting\\server.py"]
        }
      }
    }
  2. Select GPT-4o or o3-mini in the AI model dropdown.

  3. ChatGPT will natively execute all 67 screenplay tools, draft prose, and render storyboards!

Option B: Via Open-WebUI / LibreChat / Custom GPT Actions

  1. Launch the server in HTTP mode (server.py --transport streamable-http --port 8000).

  2. Open Open-WebUI Settings $\rightarrow$ Tools $\rightarrow$ Add MCP Server URL: http://localhost:8000/mcp.

  3. Select GPT-4o as your active LLM.


4. Live Integration with VS Code "Better Fountain" Extension

This server natively generates industry-standard Fountain 1.1 screenplay files (.story/screenplay.fountain).

  1. Install the Better Fountain extension in VS Code.

  2. Open d:\Studio\MCP -Storywriting\.story\screenplay.fountain.

  3. Whenever Claude or the MCP engine commits screenplay scenes, Better Fountain instantly updates:

    • Live side-by-side formatted screenplay preview

    • Real-time page count and scene duration estimates

    • Interactive scene outline sidebar


16 Production Tool Categories (67 MCP Tools)

  1. Category A: Concept & Brainstorming (4 tools): initialize_story_project, brainstorm_high_concept, develop_thematic_core, generate_title_bank.

  2. Category B: Character Architect & Dynamics (4 tools): create_character_profile, map_character_relationships, generate_character_backstory, generate_name_bank.

  3. Category C: World-Building & Lore Engine (4 tools): build_setting_location, define_world_rules, create_faction_or_culture, generate_world_timeline.

  4. Category D: Structural Plotting & Beat Sheets (5 tools): generate_beat_sheet, weave_subplots, outline_scene, calculate_pacing_and_stakes, import_one_line_orders_file.

  5. Category E: Interactive Drafting Engine (5 tools): draft_scene_prose, write_dialogue_pass, expand_sensory_details, propose_branching_options, generate_cliffhanger_or_twist.

  6. Category F: Story Doctor & Continuity (4 tools): check_narrative_continuity, scene_doctor_diagnostic, rebalance_show_vs_tell, analyze_pacing_and_rhythm.

  7. Category G: Screenplay Adaptation & Export (4 tools): narrative_to_scene_breakdown, generate_fountain_scene, export_screenplay, approve_and_commit_screenplay_scene.

  8. Category H: Storyboard Engine (3 tools): generate_storyboard_shotlist, update_frame_approval, render_storyboard_html.

  9. Category I: Character Voice & Dialogue Polish (4 tools): dialect_and_subtext_tuner, dialogue_rhythm_and_meter_analyzer, character_arc_tracker, generate_character_voice_bible.

  10. Category J: Screenplay Timing & Analytics (4 tools): estimate_screenplay_runtime, character_screen_time_matrix, scene_tension_and_pacing_heat_map, screenplay_table_read_simulator.

  11. Category K: Visual Directing, Camera & Audio (5 tools): soundtrack_and_audio_cues_designer, color_palette_and_lighting_guide, aspect_ratio_and_lens_advisor, scene_transitional_hook_generator, motif_and_symbolism_tracker.

  12. Category L: Line Production & Stripboards (4 tools): stripboard_element_breakdown, day_night_location_grouping, vfx_and_stunt_manifest, fountain_syntax_linter.

  13. Category M: Pitch Deck & Marketing Suite (4 tools): generate_pitch_deck_outline, generate_synopsis_suite, comparable_titles_analyzer, audience_emotional_engagement_predictor.

  14. Category N: Writers' Room Mechanics (6 tools): pitch_alternative_endings, generate_character_interview, red_herring_and_twist_architect, character_archetype_chemistry_analyzer, magic_or_tech_limitation_auditor, act_climax_escalator.

  15. Category O: Multi-Format Exporters (5 tools): comic_book_page_script_converter, fountain_to_epub_markdown, subtext_and_unspoken_desire_doctor, world_sensory_palette_builder, storyboard_frame_prompter.

  16. Category P: Generic Batch Execution Engine (2 tools): ingest_any_outline_file, generate_batch_screenplay.


⚡ Quick Start: Running Local CLI Modes

# Local stdio mode (Claude Desktop, Antigravity, Cursor)
& "d:\Studio\MCP -Storywriting\venv\Scripts\python.exe" server.py --transport stdio

# Streamable HTTP mode (Claude Connectors / Web UI / ChatGPT)
& "d:\Studio\MCP -Storywriting\venv\Scripts\python.exe" server.py --transport streamable-http --port 8000

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    A stateless MCP server for AI film and video production that tracks project state, shot status, and updates, enabling consistent characters and continuity across generative video tools.
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    MCP server for managing a writer's bible, a structured and searchable knowledge base of a narrative universe with tools for characters, places, events, and semantic search.
    -
  • A
    license
    Not graded
    quality
    A
    maintenance
    A locally-run MCP server that connects to Twine's story library, enabling AI-assisted story management, passage editing, link-graph analysis, and narrative intelligence from any MCP-compatible client.
    48 npm
    3
    MIT